© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23035
    Prev
    Next
    INDEX
    Explanations

    people's names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gers
    -0.13
    ðŁı»
    -0.13
    åĦ¿
    -0.11
    ooter
    -0.10
    ly
    -0.10
    irst
    -0.10
     вÑģего
    -0.10
    è¿Ļä¹Ł
    -0.09
    aran
    -0.09
    ìĦł
    -0.09
    POSITIVE LOGITS
    oup
    0.10
    hood
    0.09
    ption
    0.09
    ately
    0.09
    ful
    0.09
    ony
    0.08
    thon
    0.08
    éĥĩ
    0.08
    ushed
    0.08
    åºł
    0.08
    Activations Density 0.088%

    No Known Activations